Pose Determination by Autonomous Robots in a Facility Context

3. The non-transitory computer-readable medium of claim 2, wherein the instructions further comprise instructions to determine a side of the object that is optimal for manipulation, wherein manipulating the object comprises manipulating the object from the determined side.

5. The non-transitory computer-readable medium of claim 4, wherein the instructions to determine the three-dimensional pose of the object further comprise instructions to, responsive to determining that no respective feature is visible, determine that the three-dimensional pose is indeterminable.

6. The non-transitory computer-readable medium of claim 5, wherein the instructions further comprise instructions to, responsive to determining that the three-dimensional pose is indeterminable, transmit an alert to a human operator.

7. The non-transitory computer-readable medium of claim 1, wherein the machine-learned model is trained using labeled images, the labels of each image indicating at least one of one or more visible features and an object type.

12. The method of claim 11, further comprising determining a side of the object that is optimal for manipulation, wherein manipulating the object comprises manipulating the object from the determined side.

14. The method of claim 13, wherein determining the three-dimensional pose of the object further comprises, responsive to determining that no respective feature is visible, determining that the three-dimensional pose is indeterminable.

15. The method of claim 14, further comprising, responsive to determining that the three-dimensional pose is indeterminable, transmitting an alert to a human operator.

16. The method of claim 10, wherein the machine-learned model is trained using labeled images, the labels of each image indicating at least one of one or more visible features and an object type.